activity
20222025
most citedResisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective

18 citations · 19 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2025

TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References

Jiahong Yu, Ziqi Wang, Hailiang Zhao +3

Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe…

cs.NI2023

Advancing Federated Learning in 6G: A Trusted Architecture with Graph-based Analysis

Wenxuan Ye, Chendi Qian, Xueli An +2

Integrating native AI support into the network architecture is an essential objective of 6G. Federated Learning (FL) emerges as a potential paradigm, facilitating decentralized AI…

cs.LG2023★ 18 cited

Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective

Zhen Qin, Feiyi Chen, Chen Zhi +2

Existing approaches defend against backdoor attacks in federated learning (FL) mainly through a) mitigating the impact of infected models, or b) excluding infected models. The form…

cs.DC2023

Scheduling Multi-Server Jobs with Sublinear Regrets via Online Learning

Hailiang Zhao, Shuiguang Deng, Zhengzhe Xiang +4

Multi-server jobs that request multiple computing resources and hold onto them during their execution dominate modern computing clusters. When allocating the multi-type resources t…

cs.DC2022★ 1 cited

The Confluence of Blockchain and 6G Network: Scenarios Analysis and Performance Assessment

Bo Li, Shuiguang Deng, Xueqiang Yan +1

Emerging advanced applications, such as smart cities, healthcare, and virtual reality, demand more challenging requirements on sixth-generation (6G) mobile networks, including the…

cs.DC2022

BlockDFL: A Blockchain-based Fully Decentralized Peer-to-Peer Federated Learning Framework

Zhen Qin, Xueqiang Yan, Mengchu Zhou +1

Federated learning (FL) enables collaborative training of machine learning models without sharing training data. Traditional FL heavily relies on a trusted centralized server. Alth…